---
title: "Analysis report for criminal incidents in Victoria"
output: 
  flexdashboard::flex_dashboard:
        storyboard: true
    #orientation: columns
    #vertical_layout: fill
    #orientation: rows
        source_code: embed
---

```{r setup, include=FALSE}
library(flexdashboard)
library(tidyverse)
library(readxl)
library(haven)
library(ggplot2)
library(kableExtra)
library(ggResidpanel)
library(bookdown)
library(plotly)
library(here)
library(dplyr)
library(naniar)
library(tidytext)
```

Introdustion {data-icon="fa-signal"}
===================================== 

Billy {data-icon="fa-signal"}
===================================== 
```{r cleandata, include=FALSE}
dat <- read_excel("data/Data_Tables_LGA_Criminal_Incidents_Year_Ending_December_2020.xlsx", sheet=2)
dat <- dat %>% 
  select(c(Year, `Police Region`, `Local Government Area`, `Incidents Recorded`)) 
```
```{r readdata, include=FALSE}
dat1 <- read.csv("data/LGA_Criminal_data2020.csv")
```

Column {data-width=650}
---
### Chart 1
    
```{r table1, message=FALSE}
dat_tot <- dat1 %>% 
  filter(`Local.Government.Area` == "Total") %>% 
  group_by(`Police.Region`) %>% 
  summarise(Total_Incidents = sum(`Incidents.Recorded`)) %>% 
  arrange(-Total_Incidents)
table1 <- dat_tot %>% 
  knitr::kable(caption = "Number of Incidents Recorded in different Police Region", align = 'c') %>% 
  kable_styling(bootstrap_options = c("striped", "hover","basic"))
table1
```
---

Some commentary about Frame 1.

Column {data-width=1200}
-------------------------------------
   
### Chart 2

```{r total,fig.cap = "Total number of incidents recorded in each police region", fig.height=8, fig.align='center',fig.width=10}
dat_var <- dat1 %>% 
  filter(`Local.Government.Area` == "Total") %>% 
  group_by(Year, `Police.Region`) %>% 
  summarise(Total_Incidents = sum(`Incidents.Recorded`))
figure1 <- ggplot(dat_var, aes(x= Year,
                               y = Total_Incidents,   
                               color = `Police.Region`))+
  geom_line() +
  geom_point() +
  scale_x_continuous(breaks=seq(2011,2020,2)) +
  theme_bw()+
  facet_wrap(~ `Police.Region`, scales = "free",ncol=2)+
  scale_fill_brewer(palette = "Dark2")
ggplotly(figure1)
```
 
### Chart 3
    
```{r north, fig.cap = "Crimial activity trend in different suburbs from North West Metro", fig.align='center', fig.height=11,fig.width=10}
dat_North <- dat1 %>% 
  filter(Police.Region == "1 North West Metro") %>% 
  select(-X)
trend <- dat_North %>% 
  group_by(Local.Government.Area, Year) %>% 
  summarise(Total_Incidents = sum(`Incidents.Recorded`)) %>% 
  arrange(-Total_Incidents) %>% 
  filter(Local.Government.Area %in% c("Melbourne", 
                                      "Hume", 
                                      "Brimbank", 
                                      "Wyndham", 
                                      "Whittlesea", 
                                      "Moreland",
                                      "Banyule",
                                      "Darebin",
                                      "Hobsons Bay",
                                      "Maribyrnong",
                                      "Melton",
                                      "Moonee Valley",
                                      "Nillumbik",
                                      "Yarra"))
figure2 <- ggplot(trend, aes(x= Year, 
                             y = Total_Incidents,
                             color = "Local.Government.Area"))+
  geom_line()+
  geom_point() +
  scale_x_continuous(breaks=seq(2011,2020,2)) +
  facet_wrap(~ `Local.Government.Area`, scales = "free",ncol=2)+
  scale_fill_brewer(palette = "Dark2")+
  theme_bw()
ggplotly(figure2)
```
Jiaying {data-icon="fa-signal"}
===================================== 

```{r read-data, include=FALSE}
criminaldata <- read_excel("data/Data_Tables_LGA_Criminal_Incidents_Year_Ending_December_2020.xlsx", sheet = 4)
```
```{r datacleaning, include=FALSE}
criminaluse <- criminaldata %>% 
  select(Year,
         `Local Government Area`,
         `Offence Subdivision`,
         `Incidents Recorded`)
```

Column {data-width=1200}
---

### Chart 1

```{r vis1, fig.width=9, fig.cap="The offence_subdivision of maximum incidents in each LGA"}
  criminalfinal<- criminaluse %>% 
  group_by(`Local Government Area`, `Offence Subdivision` ) %>% 
    summarise(incidents = sum(`Incidents Recorded`)) 
data<- criminalfinal %>% arrange(desc(incidents)) %>%
slice(1) %>% 
ggplot(aes(`Local Government Area`,
       incidents,
       fill = `Offence Subdivision` )) +
  geom_col()+
   ggtitle("The offence_subdivision of maximum incidents in each LGA")+
  theme(axis.text.x = element_blank()) 
 ggplotly(data)
```

```{r vis2, fig.width=10, fig.cap="Each offence_subdivision's incidents in each year"}
  criminalfinal2<- criminaluse %>% 
  group_by(Year,`Offence Subdivision` ) %>% 
    summarise(incidents = sum(`Incidents Recorded`)) %>% 
ggplot(aes(Year,
       incidents,
       color = `Offence Subdivision` )) +
  geom_line()+
   ggtitle("Each offence_subdivision's incidents in each year")
 ggplotly(criminalfinal2)
```

Column {data-width=1000}
--------------------------------
### Chart 2

```{r datacleaning2, include=FALSE}
criminaluse2 <- criminaldata %>% 
  select(Year,
         `Offence Subgroup`,
         `Offence Subdivision`,
         `Incidents Recorded`) %>% 
  filter(`Offence Subdivision` == "B40 Theft")
```
```{r vis3, fig.width=10, fig.cap="Incidents of each offence_subgroup in most recorded offence_subdivision"}
  criminalfinal3<- criminaluse2 %>% 
  group_by(Year, `Offence Subgroup`) %>% 
    summarise(incidents = sum(`Incidents Recorded`)) %>% 
ggplot(aes(Year,
       incidents,
       fill = `Offence Subgroup` )) +
  geom_col()+
   ggtitle("Incidents of each offence_subgroup in most recorded offence_subdivision")
 ggplotly(criminalfinal3)
```

### Chart 3

```{r datacleaning3, include=FALSE}
criminaluse3 <- criminaldata %>% 
  select(Year,
         `Offence Subgroup`,
         `Incidents Recorded`)
```
```{r vis4, fig.width=10, fig.cap="Incidents of each offence_subgroup"}
  criminalfinal4<- criminaluse3 %>% 
  group_by(Year, `Offence Subgroup`) %>% 
    summarise(incidents = sum(`Incidents Recorded`)) %>% 
  arrange(desc(incidents)) %>% 
  head(100) %>% 
ggplot(aes(Year,
       incidents,
       color = `Offence Subgroup` )) +
  geom_line()+
   ggtitle("Incidents of each offence_subgroup")
 ggplotly(criminalfinal4)
```

Karan{data-icon="fa-signal"}
===================================== 
```{r read-file,include=FALSE}
data3 <- read_excel(here::here("data/Data_Tables_LGA_Criminal_Incidents_Year_Ending_December_2020.xlsx"),sheet = 4)
```

```{r clean,include=FALSE}
miss_var_summary(data3)
data3 <- data3 %>% 
  rename(Month = `Year ending`,
         LGA = `Local Government Area`,
         Suburb = `Suburb/Town Name`,
         Offence_Division = `Offence Division`,
         Offence_Subdivision = `Offence Subdivision`,
         Offence_Subgroup = `Offence Subgroup`,
         Incidents_Recorded = `Incidents Recorded`)
```

Column {data-width=1200}
---

### Chart 1

```{r Q1-table,echo=FALSE}
data3 %>% 
  group_by(Suburb) %>%
  summarise(Total_Incidents = sum(Incidents_Recorded)) %>% 
  slice_max(Total_Incidents,n = 10) %>% 
  kable(caption = "Suburbs with maximum incidents over the years") %>% 
  kable_styling(bootstrap_options = c("striped","hover","basic"))
```
Column {data-width=350}
--------------------------------
### Chart 2

```{r Q1,echo=FALSE,fig.width=8,fig.height=15,fig.cap="Top 10 Suburb with most incidents recorded"}
data3 %>% 
  group_by(Year,Suburb) %>%
  summarise(Total_Incidents = sum(Incidents_Recorded)) %>% 
  arrange(Year,desc(Total_Incidents)) %>% 
  slice_max(Total_Incidents,n = 10) %>% 
  mutate(Suburb1 = reorder_within(Suburb,Total_Incidents,Year)) %>% 
  ggplot(aes(x=Total_Incidents ,
             y=Suburb1,
             fill = Suburb)) +
  geom_col() +
  geom_text(aes(label = Total_Incidents)) +
  scale_y_reordered() +
  ylab("Suburb") +
  xlab("No. of Incidents") +
  ggtitle("Top 10 Suburb with most incidents recorded in each Years") +
  facet_wrap(~Year,ncol = 1, scales = "free")
```

### Chart 3

```{r Q2,echo=FALSE,fig.width=12,fig.height=15,fig.cap="Top 10 Offences recorded"}
data3 %>%
  mutate(lgth = str_length(Offence_Subdivision)) %>% 
  mutate(Offence_Subdivision = substr(Offence_Subdivision,start = 5,stop = lgth)) %>% 
  mutate(Offence_Subdivision = str_replace(Offence_Subdivision,"r crimes against the person","Other crimes against the person")) %>% 
  group_by(Year,Offence_Subdivision) %>% 
  summarise(Tot_incidents = sum(Incidents_Recorded)) %>% 
  arrange(Year,desc(Tot_incidents)) %>%
  slice_max(Tot_incidents,n = 10) %>% 
  mutate(Offence1 = reorder_within(Offence_Subdivision,Tot_incidents,Year)) %>% 
    ggplot(aes(y= Offence1,
         x= Tot_incidents,
         fill = Offence_Subdivision)) +
  geom_col() +
  geom_text(aes(label = Tot_incidents)) +
  scale_y_reordered() +
  ylab("Type of Offece") +
  xlab("No of Incidents") +
  facet_wrap(~Year,ncol = 1,scales = "free")
```
### Chart 4
```{r Q3,echo=FALSE,fig.width=10,fig.height=4,fig.cap="Top 10 Offfences Suburrb wise"}
Suburb_imp <- data3 %>% 
  group_by(Year,Suburb) %>%
  summarise(Total_Incidents = sum(Incidents_Recorded)) %>% 
  arrange(Year,desc(Total_Incidents)) %>% 
  slice_max(Total_Incidents,n = 10) 
Q3graph <- data3 %>% 
  mutate(lgth = str_length(Offence_Subdivision)) %>% 
  mutate(Offence_Subdivision = substr(Offence_Subdivision,start = 5,stop = lgth)) %>% 
  mutate(Offence_Subdivision = str_replace(Offence_Subdivision,"r crimes against the person","Other crimes against the person")) %>% 
  filter(Suburb %in% unique(Suburb_imp$Suburb)) %>% 
  group_by(Suburb,Offence_Subdivision) %>% 
  summarise(Tot_incidents = sum(Incidents_Recorded)) %>% 
  slice_max(Tot_incidents,n = 2) %>% 
  arrange(-Tot_incidents) %>% 
  #mutate(offence1 = reorder_within(Offence_Subdivision,Tot_incidents,Suburb)) %>% 
  ggplot(aes(y= Suburb,
             x =Tot_incidents,
             fill = Offence_Subdivision)) +
  geom_col() 
  ggplotly(Q3graph)
```
### Chart 5
```{r Q4,echo=FALSE,fig.width=10,fig.height=10,Fg.cap="Trend of Top 2 Offences in each year w.r.t Suburb" }
Q4graoh <- data3 %>% 
  mutate(lgth = str_length(Offence_Subdivision)) %>% 
  mutate(Offence_Subdivision = substr(Offence_Subdivision,start = 5,stop = lgth)) %>% 
  mutate(Offence_Subdivision = str_replace(Offence_Subdivision,"r crimes against the person","Other crimes against the person")) %>% 
  filter(Suburb %in% unique(Suburb_imp$Suburb)) %>% 
  group_by(Year,Suburb,Offence_Subdivision) %>% 
  summarise(Tot_incidents = sum(Incidents_Recorded)) %>% 
  slice_max(Tot_incidents,n = 2) %>% 
  ggplot(aes(x= as.numeric(Year),
             y =Tot_incidents,
             color = Offence_Subdivision)) +
  geom_line() +
  geom_point() +
  scale_x_continuous(breaks=seq(2011,2020,2)) +
  xlab("Year") +
  ylab("Total_incidents") +
  facet_wrap(~Suburb)
ggplotly(Q4graoh)
```

Conclusion {data-icon="fa-table"}
=====================================